{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:37:11Z","timestamp":1782833831699,"version":"3.54.5"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2108085UD12"],"award-info":[{"award-number":["2108085UD12"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3430473","type":"journal-article","created":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T17:32:41Z","timestamp":1722619961000},"page":"4488-4500","source":"Crossref","is-referenced-by-count":11,"title":["Graph-DETR4D: Spatio-Temporal Graph Modeling for Multi-View 3D Object Detection"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1843-4478","authenticated-orcid":false,"given":"Zehui","family":"Chen","sequence":"first","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Chen","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer, Electrical and Mathematical Sciences and Engineering, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiquan","family":"Zhang","sequence":"additional","affiliation":[{"name":"SenseTime Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangji","family":"Fang","sequence":"additional","affiliation":[{"name":"SenseTime Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5509-7247","authenticated-orcid":false,"given":"Qinhong","family":"Jiang","sequence":"additional","affiliation":[{"name":"SenseTime Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7266-5579","authenticated-orcid":false,"given":"Feng","family":"Wu","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6767-8105","authenticated-orcid":false,"given":"Feng","family":"Zhao","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206276"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/pres.1997.6.4.355"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2952201"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00938"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00889"},{"key":"ref8","first-page":"1","article-title":"Learning efficient object detection models with knowledge distillation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Chen"},{"key":"ref9","article-title":"Polar parametrization for vision-based surround-view 3D detection","author":"Chen","year":"2022","journal-title":"arXiv:2206.10965"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.236"},{"key":"ref11","article-title":"BEVDistill: Cross-modal BEV distillation for multi-view 3D object detection","author":"Chen","year":"2022","journal-title":"arXiv:2211.09386"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547859"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/116"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00775"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01169"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2018.8665155"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00219"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"issue":"7","key":"ref19","first-page":"1","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. Workshop","volume":"2","author":"Hinton"},{"key":"ref20","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022","journal-title":"arXiv:2203.17054"},{"key":"ref21","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv:2112.11790"},{"key":"ref22","article-title":"TiG-BEV: Multi-view BEV 3D object detection via target inner-geometry learning","author":"Huang","year":"2022","journal-title":"arXiv:2212.13979"},{"key":"ref23","article-title":"Like what you like: Knowledge distill via neuron selectivity transfer","author":"Huang","year":"2017","journal-title":"arXiv:1707.01219"},{"key":"ref24","article-title":"LET-3D-AP: Longitudinal error tolerant 3D average precision for camera-only 3D detection","author":"Hung","year":"2022","journal-title":"arXiv:2206.07705"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3274479"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3203213"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3333838"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3272170"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.776"},{"key":"ref32","article-title":"BEVStereo: Enhancing depth estimation in multi-view 3D object detection with dynamic temporal stereo","author":"Li","year":"2022","journal-title":"arXiv:2209.10248"},{"key":"ref33","first-page":"1","article-title":"Unifying voxel-based representation with transformer for 3D object detection","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref37","article-title":"Sparse4D: Multi-view 3D object detection with sparse spatial\u2013temporal fusion","author":"Lin","year":"2022","journal-title":"arXiv:2211.10581"},{"key":"ref38","article-title":"Sparse4D V2: Recurrent temporal fusion with sparse model","author":"Lin","year":"2023","journal-title":"arXiv:2305.14018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180210"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref41","article-title":"PETRv2: A unified framework for 3D perception from multi-camera images","author":"Liu","year":"2022","journal-title":"arXiv:2206.01256"},{"key":"ref42","article-title":"BEVFusion: Multi-task multi-sensor fusion with unified Bird\u2019s-eye view representation","author":"Liu","year":"2022","journal-title":"arXiv:2205.13542"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref44","article-title":"Time will tell: New outlooks and a baseline for temporal multi-view 3D object detection","author":"Park","year":"2022","journal-title":"arXiv:2210.02443"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_8"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00377"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018851"},{"key":"ref49","article-title":"Orthographic feature transform for monocular 3D object detection","author":"Roddick","year":"2018","journal-title":"arXiv:1811.08188"},{"key":"ref50","first-page":"1","article-title":"FitNets: Hints for thin deep nets","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Romero"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3039378"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref56","article-title":"MV-FCOS3D++: Multi-View camera-only 4D object detection with pretrained monocular backbones","author":"Wang","year":"2022","journal-title":"arXiv:2207.12716"},{"key":"ref57","first-page":"1475","article-title":"Probabilistic and geometric depth: Detecting objects in perspective","volume-title":"Proc. Conf. Robot Learn.","author":"Wang"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"ref60","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. Conf. Robot Learn.","author":"Wang"},{"key":"ref61","first-page":"20745","article-title":"Object DGCNN: 3D object detection using dynamic graphs","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Wang"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3245337"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02066"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_8"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02070"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00460"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref69","first-page":"1","article-title":"Improve object detection with feature-based knowledge distillation: Towards accurate and efficient detectors","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00350"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10346232\/10622019.pdf?arnumber=10622019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T04:08:00Z","timestamp":1725163680000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10622019\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3430473","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}